부산대학교 도서관

A novel architecture for information processing, called the hypernetwork architecture is described here. This model is based on the hierarchical organization and principles of biological information processing. The hypernetwork model has a representation of the molecular, cellular, and organismic levels of biological organization. Molecules are enzyme-like structures, and interactions are typical activation and inhibition processes. The representation of molecules and their interactions is comprised of binary strings and string matching respectively. Molecules are placed in cells, modeled by cellular automata. An organized group of cells forms an organism. Cell to cell interactions are produced by the effector-receptor molecules of the cells. The hypernetwork receives environmental influences at its input cells, creates cascades of molecular interactions inside the cells, passing through internal cells, and delivers an output from its output cells. Hypernetwork organisms learn classification tasks, including graph classification, by an adaptive algorithm based on molecular evolution. An organism is reproduced with random molecular mutation and the selection chooses the organism with the best structure for the problem to be solved. With its molecule based variation-selection learning algorithm, the hypernetwork is able to learn fairly complex classification tasks. Besides learning, the hypernetwork exhibits mutation buffering capabilities, intracellular feedback regulation, and can be used as a tool for understanding how hierarchies work, for studying evolutionary strategies, and as a model for building molecular computers.